Data-driven Approaches for Information Structure Identification
نویسندگان
چکیده
This paper investigates automatic identification of Information Structure (IS) in texts. The experiments use the Prague Dependency Treebank which is annotated with IS following the Praguian approach of Topic Focus Articulation. We automatically detect t(opic) and f(ocus), using node attributes from the treebank as basic features and derived features inspired by the annotation guidelines. We present the performance of decision trees (C4.5), maximum entropy, and rule induction (RIPPER) classifiers on all tectogrammatical nodes. We compare the results against a baseline system that always assigns f(ocus) and against a rule-based system. The best system achieves an accuracy of 90.69%, which is a 44.73% improvement over the baseline (62.66%).
منابع مشابه
Data-Driven Approaches to Improve the Quality of Clinical Processes: A Systematic Review
Background: Considering the emergence of electronic health records and their related technologies, an increasing attention is paid to data driven approaches like machine learning, data mining, and process mining. The aim of this paper was to identify and classify these approaches to enhance the quality of clinical processes. Methods: In order to determine the knowledge related to the research ...
متن کاملIdentification of BKCa channel openers by molecular field alignment and patent data-driven analysis
In this work, we present the first comprehensive molecular field analysis of patent structures on how the chemical structure of drugs impacts the biological binding. This task was formulated as searching for drug structures to reveal shared effects of substitutions across a common scaffold and the chemical features that may be responsible. We used the SureChEMBL patent database, which prov...
متن کاملIntelligent identification of vehicle’s dynamics based on local model network
This paper proposes an intelligent approach for dynamic identification of the vehicles. The proposed approach is based on the data-driven identification and uses a high-performance local model network (LMN) for estimation of the vehicle’s longitudinal velocity, lateral acceleration and yaw rate. The proposed LMN requires no pre-defined standard vehicle model and uses measurement data to identif...
متن کاملA comparison between knowledge-driven fuzzy and data-driven artificial neural network approaches for prospecting porphyry Cu mineralization; a case study of Shahr-e-Babak area, Kerman Province, SE Iran
The study area, located in the southern section of the Central Iranian volcano–sedimentary complex, contains a large number of mineral deposits and occurrences which is currently facing a shortage of resources. Therefore, the prospecting potential areas in the deeper and peripheral spaces has become a high priority in this region. Different direct and indirect methods try to predict promising a...
متن کاملEvaluation of Static and Dynamic Methods for Determining the Bearing Capacity of the Driven Pipe Piles (TECHNICAL NOTE)
Determination of the pile capacity is always a major concern for the safe geotechnical engineering design. Different direct and indirect methods have been proposed for determining pile bearing capacity such as static and dynamic approaches. Each method depends on the condition of the soil and type of pile as well as accessibility to necessary information. In this study bearing capacity of drive...
متن کاملتأثیر ساختواژهها در تجزیه وابستگی زبان فارسی
Data-driven systems can be adapted to different languages and domains easily. Using this trend in dependency parsing was lead to introduce data-driven approaches. Existence of appreciate corpora that contain sentences and theirs associated dependency trees are the only pre-requirement in data-driven approaches. Despite obtaining high accurate results for dependency parsing task in English langu...
متن کامل